Diagnosis of Parkinson’s Diseases with MDVP Features Using Machine Learning Approaches

Parkinson’s disease is a neurodegenerative disorder that poses a significant global health challenge. Its prevalence has prompted the urgent need for fast and immediate diagnosis to enable timely intervention and treatment planning. Parkinson’s disease causes both motor and non-motor symptoms necessitating a comprehensive approach to prediction. This research explores the intricacies of Parkinson’s disease prediction, highlighting the importance of multi-dimensional data analysis. Acknowledging the evolving landscape of medical research, the study advocates for a comprehensive approach to enhance the early detection of Parkinson’s disease, provides significant insights on the possibilities of machine learning techniques for improved patient outcomes, particularly focusing on the distinctive features offered by MDVP (Multidimensional Voice Program). Including MDVP features enhances the predictive capabilities of the models, offering a novel perspective for accurate early detection and applying machine learning models like AdaBoost, Multilayer Perceptron, Decision Tree, Random Forest, Logistic Regression, K-nearest Neighbors, Support Vector Machine (SVM), Gradient Boosting, & Naïve Bayes. This research explores the intricacies of Parkinson’s disease prediction. Results highlight the remarkable performance of the Support Vector Machine, achieving an accuracy of 98.98% & Gradient Boosting, 97.28% accuracy with the feature selection technique XGBoost and SelectKBest underscoring the significance of MDVP features in refining the predictive accuracy. This study leads to continuous efforts for the improvement of diagnostic accuracy and prognosis for Parkinson’s disease, emphasizing the importance of integrating MDVP features within the machine learning framework.